Submit a model

Know an open-weight TTS or STT model we're missing? Send the Hugging Face or GitHub link and we'll verify it and add it, usually within a week.

Open a submission (placeholder link)

Model authors: want your model benchmarked first, or a featured listing? Mention it in the submission.

New open speech models, tested. Weekly.

One email when a model ships: license, memory, and real speed on a Mac, a gaming GPU and a cloud GPU.